path: root/kernel/sched/cpufreq_schedutil.c

// SPDX-License-Identifier: GPL-2.0
/*
 * CPUFreq governor based on scheduler-provided CPU utilization data.
 *
 * Copyright (C) 2016, Intel Corporation
 * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include "sched.h"

#include <linux/sched/cpufreq.h>
#include <trace/events/power.h>

#define IOWAIT_BOOST_MIN	(SCHED_CAPACITY_SCALE / 8)

struct sugov_tunables {
	struct gov_attr_set	attr_set;
	unsigned int		rate_limit_us;
};

struct sugov_policy {
	struct cpufreq_policy	*policy;

	struct sugov_tunables	*tunables;
	struct list_head	tunables_hook;

	raw_spinlock_t		update_lock;	/* For shared policies */
	u64			last_freq_update_time;
	s64			freq_update_delay_ns;
	unsigned int		next_freq;
	unsigned int		cached_raw_freq;

	/* The next fields are only needed if fast switch cannot be used: */
	struct			irq_work irq_work;
	struct			kthread_work work;
	struct			mutex work_lock;
	struct			kthread_worker worker;
	struct task_struct	*thread;
	bool			work_in_progress;

	bool			limits_changed;
	bool			need_freq_update;
};

struct sugov_cpu {
	struct update_util_data	update_util;
	struct sugov_policy	*sg_policy;
	unsigned int		cpu;

	bool			iowait_boost_pending;
	unsigned int		iowait_boost;
	u64			last_update;

	unsigned long		util;
	unsigned long		bw_dl;
	unsigned long		max;

	/* The field below is for single-CPU policies only: */
#ifdef CONFIG_NO_HZ_COMMON
	unsigned long		saved_idle_calls;
#endif
};

static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu);

/************************ Governor internals ***********************/

static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
{
	s64 delta_ns;

	/*
	 * Since cpufreq_update_util() is called with rq->lock held for
	 * the @target_cpu, our per-CPU data is fully serialized.
	 *
	 * However, drivers cannot in general deal with cross-CPU
	 * requests, so while get_next_freq() will work, our
	 * sugov_update_commit() call may not for the fast switching platforms.
	 *
	 * Hence stop here for remote requests if they aren't supported
	 * by the hardware, as calculating the frequency is pointless if
	 * we cannot in fact act on it.
	 *
	 * This is needed on the slow switching platforms too to prevent CPUs
	 * going offline from leaving stale IRQ work items behind.
	 */
	if (!cpufreq_this_cpu_can_update(sg_policy->policy))
		return false;

	if (unlikely(sg_policy->limits_changed)) {
		sg_policy->limits_changed = false;
		sg_policy->need_freq_update = true;
		return true;
	}

	delta_ns = time - sg_policy->last_freq_update_time;

	return delta_ns >= sg_policy->freq_update_delay_ns;
}

static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
				   unsigned int next_freq)
{
	if (sg_policy->need_freq_update)
		sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
	else if (sg_policy->next_freq == next_freq)
		return false;

	sg_policy->next_freq = next_freq;
	sg_policy->last_freq_update_time = time;

	return true;
}

static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time,
			      unsigned int next_freq)
{
	if (sugov_update_next_freq(sg_policy, time, next_freq))
		cpufreq_driver_fast_switch(sg_policy->policy, next_freq);
}

static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time,
				  unsigned int next_freq)
{
	if (!sugov_update_next_freq(sg_policy, time, next_freq))
		return;

	if (!sg_policy->work_in_progress) {
		sg_policy->work_in_progress = true;
		irq_work_queue(&sg_policy->irq_work);
	}
}

/**
 * get_next_freq - Compute a new frequency for a given cpufreq policy.
 * @sg_policy: schedutil policy object to compute the new frequency for.
 * @util: Current CPU utilization.
 * @max: CPU capacity.
 *
 * If the utilization is frequency-invariant, choose the new frequency to be
 * proportional to it, that is
 *
 * next_freq = C * max_freq * util / max
 *
 * Otherwise, approximate the would-be frequency-invariant utilization by
 * util_raw * (curr_freq / max_freq) which leads to
 *
 * next_freq = C * curr_freq * util_raw / max
 *
 * Take C = 1.25 for the frequency tipping point at (util / max) = 0.8.
 *
 * The lowest driver-supported frequency which is equal or greater than the raw
 * next_freq (as calculated above) is returned, subject to policy min/max and
 * cpufreq driver limitations.
 */
static unsigned int get_next_freq(struct sugov_policy *sg_policy,
				  unsigned long util, unsigned long max)
{
	struct cpufreq_policy *policy = sg_policy->policy;
	unsigned int freq = arch_scale_freq_invariant() ?
				policy->cpuinfo.max_freq : policy->cur;

	freq = map_util_freq(util, freq, max);

	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
		return sg_policy->next_freq;

	sg_policy->cached_raw_freq = freq;
	return cpufreq_driver_resolve_freq(policy, freq);
}

/*
 * This function computes an effective utilization for the given CPU, to be
 * used for frequency selection given the linear relation: f = u * f_max.
 *
 * The scheduler tracks the following metrics:
 *
 *   cpu_util_{cfs,rt,dl,irq}()
 *   cpu_bw_dl()
 *
 * Where the cfs,rt and dl util numbers are tracked with the same metric and
 * synchronized windows and are thus directly comparable.
 *
 * The cfs,rt,dl utilization are the running times measured with rq->clock_task
 * which excludes things like IRQ and steal-time. These latter are then accrued
 * in the irq utilization.
 *
 * The DL bandwidth number otoh is not a measured metric but a value computed
 * based on the task model parameters and gives the minimal utilization
 * required to meet deadlines.
 */
unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
				 unsigned long max, enum schedutil_type type,
				 struct task_struct